mshunshin / segnetcmr Goto Github PK

first,Thank u for sharing your program. But I have some Errors about MaxpoolwithArgx.
I use tf1.4 and python 3.5.4, but it shows this error:

Could not add gradient for MaxPoolWithArgMax, Likely installed already (tf 1.4)
"Registering two gradient with name 'MaxPoolWithArgmax' !(Previous registration was in runcode C:\python35\lib\idlelib\run.py:357)"
loading images
finished loading images
Number of examples found: 526
loading images
finished loading images
Number of examples found: 279
Last trained iteration was: 0
Exception
OOM when allocating tensor with shape[6,64,128,128]
[[Node: pool2/conv2_1/conv/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](pool1/maxpool1, pool2/conv2_1/conv/kernel/read)]]
[[Node: Mean_1/_343 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_3247_Mean_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

Caused by op 'pool2/conv2_1/conv/Conv2D', defined at:
File "", line 1, in
File "C:\python35\lib\idlelib\run.py", line 130, in main
ret = method(*args, **kwargs)
File "C:\python35\lib\idlelib\run.py", line 357, in runcode
exec(code, self.locals)
File "B:\SegNetCMR-master\train.py", line 124, in
main()
File "B:\SegNetCMR-master\train.py", line 46, in main
logits, softmax_logits = tfmodel.inference(images, class_inc_bg=2)
File "B:\SegNetCMR-master\tfmodel\inference.py", line 46, in inference
net = c2rb(net, 128, [3, 3], scope='conv2_1')
File "B:\SegNetCMR-master\tfmodel\inference.py", line 28, in c2rb
name='conv')
File "C:\python35\lib\site-packages\tensorflow\python\layers\convolutional.py", line 608, in conv2d
return layer.apply(inputs)
File "C:\python35\lib\site-packages\tensorflow\python\layers\base.py", line 671, in apply
return self.call(inputs, *args, **kwargs)
File "C:\python35\lib\site-packages\tensorflow\python\layers\base.py", line 575, in call
outputs = self.call(inputs, *args, **kwargs)
File "C:\python35\lib\site-packages\tensorflow\python\layers\convolutional.py", line 167, in call
outputs = self._convolution_op(inputs, self.kernel)
File "C:\python35\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 835, in call
return self.conv_op(inp, filter)
File "C:\python35\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 499, in call
return self.call(inp, filter)
File "C:\python35\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 187, in call
name=self.name)
File "C:\python35\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 630, in conv2d
data_format=data_format, name=name)
File "C:\python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "C:\python35\lib\site-packages\tensorflow\python\framework\ops.py", line 2956, in create_op
op_def=op_def)
File "C:\python35\lib\site-packages\tensorflow\python\framework\ops.py", line 1470, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[6,64,128,128]
[[Node: pool2/conv2_1/conv/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](pool1/maxpool1, pool2/conv2_1/conv/kernel/read)]]
[[Node: Mean_1/_343 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_3247_Mean_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

Checkpoint Saved
Stopping

I got many errors related to the print statement.
File "train.py", line 82
print(f"Reached MAX_STEP: {MAX_STEP} at step: {global_step_value}")
^
SyntaxError: invalid syntax

After running python train.py, I'm getting the following error:

No OpKernel was registered to support Op 'MaxPoolWithArgmax' with these attrs. Registered devices: [CPU], Registered kernels:

Anyone has encountered this?

Shahar

In Sunnybrook dataset there are counters for both epicardium and endocardium . your code is generating masks for left ventricle, a single mask as a whole. can you tell me please the mask is covering the endocardium left ventricle area or epicardium left ventricle area.??

Thank you for the great work
i run the train.py and system says that : Cannot feed value of shape (0,) for Tensor 'Placeholder:0', which has shape '(6, 256, 256, 1)'
How can i solve this problems?

Hi, great work! As far as I can see you are training the full network from scratch, is there a reason why you don't initialise the encoder weights from a pretrained VGG-16 (first 13 layers) as in the SegNet paper?

Whether this model has been published in relevant literature, I hope to see some detailed descriptions of the network in the literature，thanks

First off, thanks for your great work. And I wonder more code example of prediction .